Journal
EUROPACE
Volume 24, Issue 10, Pages 1645-1654Publisher
OXFORD UNIV PRESS
DOI: 10.1093/europace/euac054
Keywords
Dilated cardiomyopathy; Deep neural network; Prognosis; Sudden cardiac death; Implantable cardioverter-defibrillator
Categories
Funding
- Netherlands Organisation for Health Research and Development (ZonMw) [104021004]
- Dutch Heart Foundation [2019B011]
- UCL Hospitals NIHR Biomedical Research Centre
- Fondation Leducq CURE-PLaN
- Netherlands Heart Foundation [2015T058]
- UMC Utrecht Fellowship Clinical Research Talent
- Netherlands Cardiovascular Research Initiative
- focus area of Applied Data Science at Utrecht University, The Netherlands
- Alexandre Suerman Stipendium
- CVON eDETECT
- [CVON-AI: 2018B017]
Ask authors/readers for more resources
Inherently explainable DNNs can detect patients at risk of LTVA, mainly driven by P-wave abnormalities.
Aims While electrocardiogram (ECG) characteristics have been associated with life-threatening ventricular arrhythmias (LTVA) in dilated cardiomyopathy (DCM), they typically rely on human-derived parameters. Deep neural networks (DNNs) can discover complex ECG patterns, but the interpretation is hampered by their 'black-box' characteristics. We aimed to detect DCM patients at risk of LTVA using an inherently explainable DNN. Methods and results In this two-phase study, we first developed a variational autoencoder DNN on more than 1 million 12-lead median beat ECGs, compressing the ECG into 21 different factors (F): FactorECG. Next, we used two cohorts with a combined total of 695 DCM patients and entered these factors in a Cox regression for the composite LTVA outcome, which was defined as sudden cardiac arrest, spontaneous sustained ventricular tachycardia, or implantable cardioverter-defibrillator treated ventricular arrhythmia. Most patients were male (n = 442, 64%) with a median age of 54 years [interquartile range (IQR) 44-62], and median left ventricular ejection fraction of 30% (IQR 23-39). A total of 115 patients (16.5%) reached the study outcome. Factors F-8 (prolonged PR-interval and P-wave duration, P < 0.005), F-15 (reduced P-wave height, P = 0.04), F-25 (increased right bundle branch delay, P = 0.02), F-27 (P-wave axis P < 0.005), and F-32 (reduced QRS-T voltages P = 0.03) were significantly associated with LTVA. Conclusion Inherently explainable DNNs can detect patients at risk of LTVA which is mainly driven by P-wave abnormalities.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available